English

运筹学学报 ›› 2010, Vol. 14 ›› Issue (1): 95-105.

• 运筹学 • 上一篇    下一篇

非一致有界费用MDP的强平均最优性条件

肖晴初, 谭杭生   

  • 出版日期:2010-03-15 发布日期:2010-03-15

 A Condition for Strong Average Optimality  of MDP with Non-uniformly Bounded Costs

XIAO Qing-Chu, TAN Hang-Sheng   

  • Online:2010-03-15 Published:2010-03-15

被引次数

2

摘要： 研究可数状态空间任意行动空间非一致性有界费用马氏决策过程(MDP)的强平均最优，给 出了使得每个常用的平均最优策略也是强平均最优的条件，并实质性的推广了Cavazos-Cadena和Fernandez-Gaucheran(Math. Meth. Oper. Res., 1996, 43: 281-300)的主要结果.

Abstract: In this paper, we consider the Markov decision processes under an average cost criterion with non- uniformly bounded cost,  denumerable state and arbitrary action spaces. Some sufficient conditions are given under which every average optimal policy is strong average optimal. We improve the main results obtained by Cavazos-Cadena R.and Fernandez-Gaucheran E. (Math. Meth. Oper. Res., 1996, 43: 281-300).